Monitoring Acute Heart Failure Patients Using Internet-of-Things-Based Smart Monitoring System.

With technological advancements, smart health monitoring systems are gaining growing importance and popularity. Today, business trends are changing from physical infrastructure to online services. With the restrictions imposed during COVID-19, medical services have been changed. The concepts of smart homes, smart appliances, and smart medical systems have gained popularity. The Internet of Things (IoT) has revolutionized communication and data collection by incorporating smart sensors for data collection from diverse sources. In addition, it utilizes artificial intelligence (AI) approaches to control a large volume of data for better use, storing, managing, and making decisions. In this research, a health monitoring system based on AI and IoT is designed to deal with the data of heart patients. The system monitors the heart patient's activities, which helps to inform patients about their health status. Moreover, the system can perform disease classification using machine learning models. Experimental results reveal that the proposed system can perform real-time monitoring of patients and classify diseases with higher accuracy.

An ensemble prediction model for COVID-19 mortality risk.

Background: It's critical to identify COVID-19 patients with a higher death risk at early stage to give them better hospitalization or intensive care. However, thus far, none of the machine learning models has been shown to be successful in an independent cohort. We aim to develop a machine learning model which could accurately predict death risk of COVID-19 patients at an early stage in other independent cohorts. Methods: We used a cohort containing 4711 patients whose clinical features associated with patient physiological conditions or lab test data associated with inflammation, hepatorenal function, cardiovascular function, and so on to identify key features. To do so, we first developed a novel data preprocessing approach to clean up clinical features and then developed an ensemble machine learning method to identify key features. Results: Finally, we identified 14 key clinical features whose combination reached a good predictive performance of area under the receiver operating characteristic curve 0.907. Most importantly, we successfully validated these key features in a large independent cohort containing 15 790 patients. Conclusions: Our study shows that 14 key features are robust and useful in predicting the risk of death in patients confirmed SARS-CoV-2 infection at an early stage, and potentially useful in clinical settings to help in making clinical decisions.

Prognostic significance of chest CT severity score in mortality prediction of COVID-19 patients, a machine learning study

Background: The high mortality rate of COVID-19 makes it necessary to seek early identification of high-risk patients with poor prognoses. Although the association between CT-SS and mortality of COVID-19 patients was reported, its prognosis significance in combination with other prognostic parameters was not evaluated yet. Method(s): This retrospective single-center study reviewed a total of 6854 suspected patients referred to Imam Khomeini hospital, Ilam city, west of Iran, from February 9, 2020 to December 20, 2020. The prognostic performances of k-Nearest Neighbors (kNN), Multilayer Perceptron (MLP), Support Vector Machine (SVM), and J48 decision tree algorithms were evaluated based on the most important and relevant predictors. The metrics derived from the confusion matrix were used to determine the performance of the ML models. Result(s): After applying exclusion criteria, 815 hospitalized cases were entered into the study. Of these, 447(54.85%) were male and the mean (+/- SD) age of participants was 57.22(+/- 16.76) years. The results showed that the performances of the ML algorithms were improved when they are fed by the dataset with CT-SS data. The kNN model with an accuracy of 94.1%, sensitivity of 100. 0%, precision of 89.5%, specificity of 88.3%, and AUC around 97.2% had the best performance among the other three ML techniques. Conclusion(s): The integration of CT-SS data with demographics, risk factors, clinical manifestations, and laboratory parameters improved the prognostic performances of the ML algorithms. An ML model with a comprehensive collection of predictors could identify high-risk patients more efficiently and lead to the optimal use of hospital resources.Copyright © 2023, The Author(s).

The impact of vaccination to clinical severity and mortality of COVID-19 patients

Background: SARS-CoV-2 was discovered in December 2019 and later become global pandemic. Preliminary studies stated that broad vaccine coverage will suppress mortality and incidence of COVID-19. Therefore, we conduct a cross-sectional study to assess the efficacy of COVID-19 vaccination. Materials and Methods: We collected secondary data from electronic medical records of 343 COVID-19 positive patients confirmed via reverse transcription polymerase chain reaction from July 2021 to December 2021. We analyzed epidemiologic data, vaccination history, baseline symptoms, comorbidity, baseline vital signs, and outcome using hypothesis testing χ 2 and logistic regression. Results: Sex had an χ 2 of 9.34 (P 0.001) while type of vaccine had an χ 2 of 1.49 (P = 0.22) to clinical severity. Age, pulse rate, respiration rate, body temperature, and Glasgow coma scale were found to be significant risk factors to clinical severity. Number of vaccines previously received was found to be a protective factor to clinical severity (odds ratio (OR) = 0.49, 95% CI = 0.32-0.74, P 0.001). We also found that sex (χ 2 = 10.42, P 0.001) was a predictor to discharge condition. Moreover, age was also found to be a significant predictor (OR = 1.03, 95% CI = 1.03-1.05, P 0.001), as well as number of symptoms (OR = 0.66, P 0.001), comorbidities (OR = 1.64, P 0.001), pulse rate (OR = 1.04, P 0.001), respiration rate (OR = 1.17, P 0.001), and Glasgow coma scale (OR = 0.72, P = 0.03). Conclusion: Age, sex, number of vaccines received, number of symptoms, number of comorbidities, pulse rate, and respiration rate were significant predictors of clinical severity and outcome in COVID-19 patients. In addition, body temperature was also a predictor for clinical severity, while Glasgow coma scale was a predictor for outcome. © 2023 Bali Journal of Anesthesiology ;Published by Wolters Kluwer - Medknow.

Comparative Study of Bun/Albumin Ratio (BAR) with D Dimer/Albumin Ratio (DAR), A Better Prognostic Indicator for Outcomes of Hospitalized COVID-19 Patients

Introduction: On December 31, 2019, China reported cases of pneumonia of unknown etiology in the city of Wuhan, Hubei Province of China. With further investigations, the Chinese health authorities, on 7th January 2020 reported the agent as the novel Coronavirus, 2019-nCOV. Initially, Wuhan and later the entire Hubei province was brought under stringent lockdown. Material(s) and Method(s): This retrospective record analysis study involving laboratory investigations was carried out in a single center in the months of June and July 2022. The ethical clearance for this single-centre study was obtained from the Institutional Ethics Committee (IEC). This study included 112 patients, of ages more than or equal to 18 years, who were confirmed cases of COVID-19 with at least one reverse transcriptase polymerase chain reaction test positive and admitted for inpatient treatment for a minimum of 8 days or longer in the wards or ICU between May 2020 to March 2022. Result(s): A total of 112 patients who had a positive RT PCR test were identified and included in the study after excluding patients who had sought discharge against medical advice, who had been referred to other hospitals and patients with a history of chronic renal failure. The mean age of patients included was 60.25 + 15.66. Among these patients 76 (67.9%) were male and 36 (32.1%) were female. Of the 112 patients, 47 patients (42%) survived of which 21(32.3%) were male, 15(31.9%) were female and 65 patients (58%) did not survive, of which 44(67.7%) were male and 21(32.3%) were female. Conclusion(s): Through this study, we can see that all the parameters considered ie. Serum Albumin, Serum Blood urea nitrogen (BUN), D dimer, BUN/Albumin ratio (BAR) and D dimer/Albumin ratio (DAR) are very solid indicators of predicting the outcome of admitted COVID-19 patients.Copyright © 2023, Dr Yashwant Research Labs Pvt Ltd. All rights reserved.

Outcome prediction in hospitalized COVID-19 patients: Comparison of the performance of five severity scores.

Background: The aim of our study was to externally validate the predictive capability of five developed coronavirus disease 2019 (COVID-19)-specific prognostic tools, including the COVID-19 Spanish Society of Infectious Diseases and Clinical Microbiology (SEIMC), Shang COVID severity score, COVID-intubation risk score-neutrophil/lymphocyte ratio (IRS-NLR), inflammation-based score, and ventilation in COVID estimator (VICE) score. Methods: The medical records of all patients hospitalized for a laboratory-confirmed COVID-19 diagnosis between May 2021 and June 2021 were retrospectively analyzed. Data were extracted within the first 24 h of admission, and five different scores were calculated. The primary and secondary outcomes were 30-day mortality and mechanical ventilation, respectively. Results: A total of 285 patients were enrolled in our cohort. Sixty-five patients (22.8%) were intubated with ventilator support, and the 30-day mortality rate was 8.8%. The Shang COVID severity score had the highest numerical area under the receiver operator characteristic (AUC-ROC) (AUC 0.836) curve to predict 30-day mortality, followed by the SEIMC score (AUC 0.807) and VICE score (AUC 0.804). For intubation, both the VICE and COVID-IRS-NLR scores had the highest AUC (AUC 0.82) compared to the inflammation-based score (AUC 0.69). The 30-day mortality increased steadily according to higher Shang COVID severity scores and SEIMC scores. The intubation rate exceeded 50% in the patients stratified by higher VICE scores and COVID-IRS-NLR score quintiles. Conclusion: The discriminative performances of the SEIMC score and Shang COVID severity score are good for predicting the 30-day mortality of hospitalized COVID-19 patients. The COVID-IRS-NLR and VICE showed good performance for predicting invasive mechanical ventilation (IMV).

BiT-MAC: Mortality prediction by bidirectional time and multi-feature attention coupled network on multivariate irregular time series.

Mortality prediction is crucial to evaluate the severity of illness and assist in improving the prognosis of patients. In clinical settings, one way is to analyze the multivariate time series (MTSs) of patients based on their medical data, such as heart rates and invasive mean arterial blood pressure. However, this suffers from sparse, irregularly sampled, and incomplete data issues. These issues can compromise the performance of follow-up MTS-based analytic applications. Plenty of existing methods try to deal with such irregular MTSs with missing values by capturing the temporal dependencies within a time series, yet in-depth research on modeling inter-MTS couplings remains rare and lacks model interpretability. To this end, we propose a bidirectional time and multi-feature attention coupled network (BiT-MAC) to capture the temporal dependencies (i.e., intra-time series coupling) and the hidden relationships among variables (i.e., inter-time series coupling) with a bidirectional recurrent neural network and multi-head attention, respectively. The resulting intra- and inter-time series coupling representations are then fused to estimate the missing values for a more robust MTS-based prediction. We evaluate BiT-MAC by applying it to the missing-data corrupted mortality prediction on two real-world clinical datasets, i.e., PhysioNet'2012 and COVID-19. Extensive experiments demonstrate the superiority of BiT-MAC over cutting-edge models, verifying the great value of the deep and hidden relations captured by MTSs. The interpretability of features is further demonstrated through a case study.

Automated prediction of COVID-19 mortality outcome using clinical and laboratory data based on hierarchical feature selection and random forest classifier.

Early prediction of COVID-19 mortality outcome can decrease expiration risk by alerting healthcare personnel to assure efficient resource allocation and treatment planning. This study introduces a machine learning framework for the prediction of COVID-19 mortality using demographics, vital signs, and laboratory blood tests (complete blood count (CBC), coagulation, kidney, liver, blood gas, and general). 41 features from 244 COVID-19 patients were recorded on the first day of admission. In this study, first, the features in each of the eight categories were investigated. Afterward, features that have an area under the receiver operating characteristic curve (AUC) above 0.6 and the p-value criterion from the Wilcoxon rank-sum test below 0.005 were used as selected features for further analysis. Then five feature reduction methods, Forward Feature selection, minimum Redundancy Maximum Relevance, Relieff, Linear Discriminant Analysis, and Neighborhood Component Analysis were utilized to select the best combination of features. Finally, seven classifiers frameworks, random forest (RF), support vector machine, logistic regression (LR), K nearest neighbors, Artifical neural network, bagging, and boosting were used to predict the mortality outcome of COVID-19 patients. The results revealed that the combination of features in CBC and then vital signs had the highest mortality classification parameters, respectively. Furthermore, the RF classifier with hierarchical feature selection algorithms via Forward Feature selection had the highest classification power with an accuracy of 92.08 ± 2.56. Therefore, our proposed method can be confidently used as a valuable assistant prognostic tool to sieve patients with high mortality risks.

COVID-19 Mortality Prediction using Machine Learning: A Deep Forest Approach

COVID-19 is an extremely deadly disease which has wreaked havoc worldwide. Initially, the first case was reported in the wet markets of Wuhan, China in the early 2020's. Though the mortality rate is low compared to other dangerous diseases, a lot of people have already succumbed to this virus. Vaccines have been successfully rolled out and it seems effective in preventing the severe symptoms of the coronavirus. However, a section of people (the elderly and people with existing comorbidities) still continue to die. It is extremely important to predict the patient vulnerability using machine learning since appropriate medicines and treatments can be given in time and precious lives can be saved. In this research, the deep forest classifier is utilized to predict the COVID-19 casualty status. This classifier requires extremely low hyperparameter tuning and can easily compete with the deep learning classifiers. This algorithm performed better than the traditional machine learning classifiers with an accuracy of 92%. The positive results obtained signifies the potential use of deep forest to prevent unwanted COVID-19 deaths by effectively deploying them in various medical facilities. Further, it can reduce the extreme burden already existing on healthcare systems caused by the novel coronavirus. © 2022 IEEE.

Predicting the evolution of COVID-19 mortality risk: A Recurrent Neural Network approach.

Background: In December 2020, the COVID-19 disease was confirmed in 1,665,775 patients and caused 45,784 deaths in Spain. At that time, health decision support systems were identified as crucial against the pandemic. Methods: This study applies Deep Learning techniques for mortality prediction of COVID-19 patients. Two datasets with clinical information were used. They included 2,307 and 3,870 COVID-19 infected patients admitted to two Spanish hospitals. Firstly, we built a sequence of temporal events gathering all the clinical information for each patient, comparing different data representation methods. Next, we used the sequences to train a Recurrent Neural Network (RNN) model with an attention mechanism exploring interpretability. We conducted an extensive hyperparameter search and cross-validation. Finally, we ensembled the resulting RNNs to enhance sensitivity. Results: We assessed the performance of our models by averaging the performance across all the days in the sequences. Additionally, we evaluated day-by-day predictions starting from both the hospital admission day and the outcome day. We compared our models with two strong baselines, Support Vector Classifier and Random Forest, and in all cases our models were superior. Furthermore, we implemented an ensemble model that substantially increased the system's sensitivity while producing more stable predictions. Conclusions: We have shown the feasibility of our approach to predicting the clinical outcome of patients. The result is an RNN-based model that can support decision-making in healthcare systems aiming at interpretability. The system is robust enough to deal with real-world data and can overcome the problems derived from the sparsity and heterogeneity of data.

Exploring Biomarker Identification and Mortality Prediction of COVID-19 Patients Using ML Algorithms

The coronavirus pandemic led to the collapse of the healthcare systems of several countries worldwide, including the highly developed ones. The sudden rise in hospitalization requirements for the patients suffering from the disease, caused a tremendous pressure not only on the healthcare system but also on the frontline workers. So, for early diagnosis and prognosis of the patients, identification of the biomarkers pertaining to the coronavirus disease became an essential requirement. Thus, a machine learning (ML) based mortality prediction model was developed that was able to predict the mortality of the patients using a combination of only six features. The six selected features included, four identified biomarkers, namely, lactate dehydrogenase (LDH), neutrophils percentage (NP), fibrin degradation products (FDP), and erythrocyte sedimentation rate (ESR);and, other two features as age and the coronavirus detection test. The developed model with a novel semiautomated method of medical data handling technique, achieved an accuracy of over 98%, and was able to predict the final outcome of the patients on an average of 8 days in advance. The corresponding work was carried out with the intent to ease the burden on the healthcare system, by providing a faster and accurate clinical assessment of the patients suffering from the coronavirus disease. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

A 9-mRNA signature measured from whole blood by a prototype PCR panel predicts 28-day mortality upon admission of critically ill COVID-19 patients.

Immune responses affiliated with COVID-19 severity have been characterized and associated with deleterious outcomes. These approaches were mainly based on research tools not usable in routine clinical practice at the bedside. We observed that a multiplex transcriptomic panel prototype termed Immune Profiling Panel (IPP) could capture the dysregulation of immune responses of ICU COVID-19 patients at admission. Nine transcripts were associated with mortality in univariate analysis and this 9-mRNA signature remained significantly associated with mortality in a multivariate analysis that included age, SOFA and Charlson scores. Using a machine learning model with these 9 mRNA, we could predict the 28-day survival status with an Area Under the Receiver Operating Curve (AUROC) of 0.764. Interestingly, adding patients' age to the model resulted in increased performance to predict the 28-day mortality (AUROC reaching 0.839). This prototype IPP demonstrated that such a tool, upon clinical/analytical validation and clearance by regulatory agencies could be used in clinical routine settings to quickly identify patients with higher risk of death requiring thus early aggressive intensive care.

Using a 29-mRNA Host Response Classifier To Detect Bacterial Coinfections and Predict Outcomes in COVID-19 Patients Presenting to the Emergency Department.

Clinicians in the emergency department (ED) face challenges in concurrently assessing patients with suspected COVID-19 infection, detecting bacterial coinfection, and determining illness severity since current practices require separate workflows. Here, we explore the accuracy of the IMX-BVN-3/IMX-SEV-3 29 mRNA host response classifiers in simultaneously detecting severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection and bacterial coinfections and predicting clinical severity of COVID-19. A total of 161 patients with PCR-confirmed COVID-19 (52.2% female; median age, 50.0 years; 51% hospitalized; 5.6% deaths) were enrolled at the Stanford Hospital ED. RNA was extracted (2.5 mL whole blood in PAXgene blood RNA), and 29 host mRNAs in response to the infection were quantified using Nanostring nCounter. The IMX-BVN-3 classifier identified SARS-CoV-2 infection in 151 patients with a sensitivity of 93.8%. Six of 10 patients undetected by the classifier had positive COVID tests more than 9 days prior to enrollment, and the remaining patients oscillated between positive and negative results in subsequent tests. The classifier also predicted that 6 (3.7%) patients had a bacterial coinfection. Clinical adjudication confirmed that 5/6 (83.3%) of the patients had bacterial infections, i.e., Clostridioides difficile colitis (n = 1), urinary tract infection (n = 1), and clinically diagnosed bacterial infections (n = 3), for a specificity of 99.4%. Two of 101 (2.8%) patients in the IMX-SEV-3 "Low" severity classification and 7/60 (11.7%) in the "Moderate" severity classification died within 30 days of enrollment. IMX-BVN-3/IMX-SEV-3 classifiers accurately identified patients with COVID-19 and bacterial coinfections and predicted patients' risk of death. A point-of-care version of these classifiers, under development, could improve ED patient management, including more accurate treatment decisions and optimized resource utilization. IMPORTANCE We assay the utility of the single-test IMX-BVN-3/IMX-SEV-3 classifiers that require just 2.5 mL of patient blood in concurrently detecting viral and bacterial infections as well as predicting the severity and 30-day outcome from the infection. A point-of-care device, in development, will circumvent the need for blood culturing and drastically reduce the time needed to detect an infection. This will negate the need for empirical use of broad-spectrum antibiotics and allow for antibiotic use stewardship. Additionally, accurate classification of the severity of infection and the prediction of 30-day severe outcomes will allow for appropriate allocation of hospital resources.

Alveolar-arterial Oxygen Gradient in COVID-19 Pneumonia Initiated on Noninvasive Ventilation: Looking into the Mortality-prediction Ability.

How to cite this article: Karim HMR, Esquinas AM. Alveolar-arterial Oxygen Gradient in COVID-19 Pneumonia Initiated on Noninvasive Ventilation: Looking into the Mortality-prediction Ability. Indian J Crit Care Med 2022;26(10):1152.

Reduce the Cold Start of COVID-19 In-hospital Mortality Prediction Models via Transfer Learning

At the beginning of the breakout of a new disease, the healthcare community almost always has little experience in treating patients of this kind. Similarly, due to insufficient patient records at the early stage of a pandemic, it is difficult to train an in-hospital mortality prediction model specific to the new disease. We call this the 'cold start' problem of mortality prediction models. In this paper, we aim to study the cold start problem of 3-days ahead COVID-19 mortality prediction models by the following two steps: (i) Train XGBoost [1] and logistic regression 3-days ahead mortality prediction models on MIMIC3, a publicly available ICU patient dataset [2];(ii) Apply those MIMIC3 models to COVID-19 patients and then use the prediction scores as a new feature to train COVID-19 3-days ahead mortality prediction models. Retrospective experiments are conducted on a real-world COVID-19 patient dataset(n = 1,287) collected in US from June 2020 to February 2021 with a mixed cohort of both ICU and Non-ICU patients. Since the dataset is imbalanced(death rate = 7.8%), we primarily focus on the relative improvement of AUPR. We trained models with and without MIMIC3 scores on the first 200, 400,..., 1000 patients respectively and then tested on the next 200 incoming patients. The results show a diminishing positive transfer effect of AUPR from 5.36% for the first 200 patients(death rate = 5.5%) to 3.58% for all 1,287 patients. Meanwhile the AUROC scores largely remain unchanged, regardless of the number of patients in the training set. What's more, the p-value of t-test suggests that the cold start problem disappears for a dataset larger than 600 COVID-19 patients. To conclude, we demonstrate the possibility of mitigating the cold start problem via the proposed method. © 2022 IEEE.

Mortality Prediction in ICU Patients Suffering from Stroke

Ischemic stroke is a medical emergency that requires hospitalization and occasionally, specialized care at the Intensive Care Unit. Mortality prediction in the ICUs has been a challenge for intensivists, since prompt identification could impact medical clinical practices and allow efficient allocation of health resources in the ICUs, which are extremely restricted, especially in the era of COVID-19 pandemic. Clinical decision support systems based on machine learning algorithms are taking advantage of the vast amount of information available in the ICUs and are becoming popular in the medical predictive analysis. This study aims to explore the feasibility of interpretable machine learning models to predict mortality in critically-ill patients suffering from stroke. To do so, a vast variety of clinical and laboratory information stored in the electronic health record, are pre-processed to allow taking into account the temporal characteristics of a patient's stay. An 8-hour sliding observation window was utilized. For the experimental evaluation we used the Medical Information Mart for Intensive Care Database (MIMIC-IV). Results indicate sufficient ability to predict mortality at the end of a given day during the patient's stay. Moreover, attribute evaluation highlights the important indicators to consider when following up with a patient. © 2022 ACM.

Leveraging Clinical BERT in Multimodal Mortality Prediction Models for COVID-19

Clinical prediction models are often based solely on the use of structured data in electronic health records, e.g. vital parameters and laboratory results, effectively ignoring potentially valuable information recorded in other modalities, such as free-text clinical notes. Here, we report on the development of a multimodal model that combines structured and unstructured data. In particular, we study how best to make use of a clinical language model in a multimodal setup for predicting 30-day all-cause mortality upon hospital admission in patients with COVID-19. We evaluate three strategies for incorporating a domain-specific clinical BERT model in multimodal prediction systems: (i) without fine-tuning, (ii) with unimodal fine-tuning, and (iii) with multimodal fine-tuning. The best-performing model leverages multimodal fine-tuning, in which the clinical BERT model is updated based also on the structured data. This multimodal mortality prediction model is shown to outperform unimodal models that are based on using either only structured data or only unstructured data. The experimental results indicate that clinical prediction models can be improved by including data in other modalities and that multimodal fine-tuning of a clinical language model is an effective strategy for incorporating information from clinical notes in multimodal prediction systems. © 2022 IEEE.

Dietary, comorbidity, and geo-economic data fusion for explainable COVID-19 mortality prediction.

Many factors significantly influence the outcomes of infectious diseases such as COVID-19. A significant focus needs to be put on dietary habits as environmental factors since it has been deemed that imbalanced diets contribute to chronic diseases. However, not enough effort has been made in order to assess these relations. So far, studies in the field have shown that comorbid conditions influence the severity of COVID-19 symptoms in infected patients. Furthermore, COVID-19 has exhibited seasonal patterns in its spread; therefore, considering weather-related factors in the analysis of the mortality rates might introduce a more relevant explanation of the disease's progression. In this work, we provide an explainable analysis of the global risk factors for COVID-19 mortality on a national scale, considering dietary habits fused with data on past comorbidity prevalence and environmental factors such as seasonally averaged temperature geolocation, economic and development indices, undernourished and obesity rates. The innovation in this paper lies in the explainability of the obtained results and is equally essential in the data fusion methods and the broad context considered in the analysis. Apart from a country's age and gender distribution, which has already been proven to influence COVID-19 mortality rates, our empirical analysis shows that countries with imbalanced dietary habits generally tend to have higher COVID-19 mortality predictions. Ultimately, we show that the fusion of the dietary data set with the geo-economic variables provides more accurate modeling of the country-wise COVID-19 mortality rates with respect to considering only dietary habits, proving the hypothesis that fusing factors from different contexts contribute to a better descriptive analysis of the COVID-19 mortality rates.

Supervised Pretraining through Contrastive Categorical Positive Samplings to Improve COVID-19 Mortality Prediction.

Clinical EHR data is naturally heterogeneous, where it contains abundant sub-phenotype. Such diversity creates challenges for outcome prediction using a machine learning model since it leads to high intra-class variance. To address this issue, we propose a supervised pre-training model with a unique embedded k-nearest-neighbor positive sampling strategy. We demonstrate the enhanced performance value of this framework theoretically and show that it yields highly competitive experimental results in predicting patient mortality in real-world COVID-19 EHR data with a total of over 7,000 patients admitted to a large, urban health system. Our method achieves a better AUROC prediction score of 0.872, which outperforms the alternative pre-training models and traditional machine learning methods. Additionally, our method performs much better when the training data size is small (345 training instances).

Learning a Battery of COVID-19 Mortality Prediction Models by Multi-objective Optimization

The COVID-19 pandemic is continuously evolving with drastically changing epidemiological situations which are approached with different decisions: from the reduction of fatalities to even the selection of patients with the highest probability of survival in critical clinical situations. Motivated by this, a battery of mortality prediction models with different performances has been developed to assist physicians and hospital managers. Logistic regression, one of the most popular classifiers within the clinical field, has been chosen as the basis for the generation of our models. Whilst a standard logistic regression only learns a single model focusing on improving accuracy, we propose to extend the possibilities of logistic regression by focusing on sensitivity and specificity. Hence, the log-likelihood function, used to calculate the coefficients in the logistic model, is split into two objective functions: one representing the survivors and the other for the deceased class. A multi-objective optimization process is undertaken on both functions in order to find the Pareto set, composed of models not improved by another model in both objective functions simultaneously. The individual optimization of either sensitivity (deceased patients) or specificity (survivors) criteria may be conflicting objectives because the improvement of one can imply the worsening of the other. Nonetheless, this conflict guarantees the output of a battery of diverse prediction models. Furthermore, a specific methodology for the evaluation of the Pareto models is proposed. As a result, a battery of COVID-19 mortality prediction models is obtained to assist physicians in decision-making for specific epidemiological situations. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.